Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19617
    Prev
    Next
    INDEX
    Explanations

    words related to tragic events involving families

    oai_token-act-pair · gpt-3.5-turbo

    references to families and their emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indal
    -0.76
    SPONSORED
    -0.70
     Kyoto
    -0.69
    hower
    -0.69
     Keynes
    -0.68
    ahime
    -0.67
    soDeliveryDate
    -0.66
    GW
    -0.65
    poll
    -0.65
    acebook
    -0.64
    POSITIVE LOGITS
     allege
    0.88
     testimonies
    0.88
     paramed
    0.87
     testimony
    0.87
     patriarch
    0.81
     coroner
    0.81
     affidav
    0.80
     plead
    0.77
     grieving
    0.76
     alleges
    0.76
    Activations Density 0.195%

    No Known Activations